regenerate

manifests/prometheus-operator-prometheusRule.yaml

@@ -0,0 +1,79 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  labels:
+    app.kubernetes.io/component: controller
+    app.kubernetes.io/name: prometheus-operator
+    app.kubernetes.io/part-of: kube-prometheus
+    app.kubernetes.io/version: 0.45.0
+    prometheus: k8s
+    role: alert-rules
+  name: prometheus-operator-rules
+  namespace: monitoring
+spec:
+  groups:
+  - name: prometheus-operator
+    rules:
+    - alert: PrometheusOperatorListErrors
+      annotations:
+        description: Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
+        summary: Errors while performing list operations in controller.
+      expr: |
+        (sum by (controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_list_operations_total{job="prometheus-operator",namespace="monitoring"}[10m]))) > 0.4
+      for: 15m
+      labels:
+        severity: warning
+    - alert: PrometheusOperatorWatchErrors
+      annotations:
+        description: Errors while performing watch operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
+        summary: Errors while performing watch operations in controller.
+      expr: |
+        (sum by (controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_watch_operations_total{job="prometheus-operator",namespace="monitoring"}[10m]))) > 0.4
+      for: 15m
+      labels:
+        severity: warning
+    - alert: PrometheusOperatorSyncFailed
+      annotations:
+        description: Controller {{ $labels.controller }} in {{ $labels.namespace }} namespace fails to reconcile {{ $value }} objects.
+        summary: Last controller reconciliation failed
+      expr: |
+        min_over_time(prometheus_operator_syncs{status="failed",job="prometheus-operator",namespace="monitoring"}[5m]) > 0
+      for: 10m
+      labels:
+        severity: warning
+    - alert: PrometheusOperatorReconcileErrors
+      annotations:
+        description: '{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.'
+        summary: Errors while reconciling controller.
+      expr: |
+        (sum by (controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]))) / (sum by (controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="prometheus-operator",namespace="monitoring"}[5m]))) > 0.1
+      for: 10m
+      labels:
+        severity: warning
+    - alert: PrometheusOperatorNodeLookupErrors
+      annotations:
+        description: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.
+        summary: Errors while reconciling Prometheus.
+      expr: |
+        rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]) > 0.1
+      for: 10m
+      labels:
+        severity: warning
+    - alert: PrometheusOperatorNotReady
+      annotations:
+        description: Prometheus operator in {{ $labels.namespace }} namespace isn't ready to reconcile {{ $labels.controller }} resources.
+        summary: Prometheus operator not ready
+      expr: |
+        min by(namespace, controller) (max_over_time(prometheus_operator_ready{job="prometheus-operator",namespace="monitoring"}[5m]) == 0)
+      for: 5m
+      labels:
+        severity: warning
+    - alert: PrometheusOperatorRejectedResources
+      annotations:
+        description: Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources.
+        summary: Resources rejected by Prometheus operator
+      expr: |
+        min_over_time(prometheus_operator_managed_resources{state="rejected",job="prometheus-operator",namespace="monitoring"}[5m]) > 0
+      for: 5m
+      labels:
+        severity: warning